Masters Theses

Author

Peng Guo

Keywords and Phrases

Cervical cancer; feature extraction; image processing; neural network

Abstract

"Cervical cancer, the second most common cancer affecting women worldwide and the most common in developing countries can be cured if detected early and treated. Expert pathologists routinely visually examine histology slides for cervix tissue abnormality assessment. In previous research, an automated, localized, fusion-based approach was investigated for classifying squamous epithelium into Normal, CIN1, CIN2, and CIN3 grades of cervical intraepithelial neoplasia (CIN) based on image analysis of 62 digitized histology images obtained through the National Library of Medicine. In this research, CIN grade assessments from two pathologists are analyzed and are used to facilitate atypical cell concentration feature development from vertical segment partitions of the epithelium region for the same digitized histology images. Using features developed in this thesis with prior work, a particle swarm optimization and Receiver Operating Characteristic curve (ROC) explored for CIN classification showing exact grade labeling accuracy as high as 90%."--Abstract, page iii.

Advisor(s)

Stanley, R. Joe

Committee Member(s)

Moss, Randy Hays, 1953-
Stoecker, William V.

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Electrical Engineering

Sponsor(s)

National Library of Medicine (U.S.)

Publisher

Missouri University of Science and Technology

Publication Date

Summer 2014

Pagination

x, 83 pages

Note about bibliography

Includes bibliographic references (pages 81-82).

Rights

© 2014 Peng Guo, All rights reserved.

Document Type

Thesis - Open Access

File Type

text

Language

English

Library of Congress Subject Headings

Cervix uteri -- Cancer
Cancer -- Histopathology
Image processing

Thesis Number

T 10510

Electronic OCLC #

894579438

Share

 
COinS